Faster Zero-shot Multi-modal Entity Linking via Visual-Linguistic Representation.

Qiushuo Zheng Hao Wen Meng Wang Guilin Qi Chaoyu Bai

Published in: Data Intell. (2022)

Keyphrases

multi modal
cross modal
multi modality
video search
high dimensional
single modality
low level
visual features
information retrieval
higher level
image annotation
multiple modalities
entity linking
natural language processing
image representation